Forecasting Electricity Demand in Turkey Using Optimization and Machine Learning Algorithms

Abstract

Medium Neural Networks (MNN), Whale Optimization Algorithm (WAO), and Support Vector Machine (SVM) methods are frequently used in the literature for estimating electricity demand. The objective of this study was to make an estimation of the electricity demand for Turkey’s mainland with the use of mixed methods of MNN, WAO, and SVM. Imports, exports, gross domestic product (GDP), and population data are used based on input data from 1980 to 2019 for mainland Turkey, and the electricity demands up to 2040 are forecasted as an output value. The performance of methods was analyzed using statistical error metrics Root Mean Square Error (RMSE), Mean Absolute Error (MAE), R-squared, and Mean Square Error (MSE). The correlation matrix was utilized to demonstrate the relationship between the actual data and calculated values and the relationship between dependent and independent variables. The p-value and confidence interval analysis of statistical methods was performed to determine which method was more effective. It was observed that the minimum RMSE, MSE, and MAE statistical errors are 5.325 × 10−14, 28.35 × 10−28, and 2.5 × 10−14, respectively. The MNN methods showed the strongest correlation between electricity demand forecasting and real data among all the applications tested.

Investigating the Drivers of Grid Electricity Demand in Nigeria: Harnessing the Power of Machine Learning and Artificial Intelligence Algorithms

“…Furthermore, as depicted in Figure 2.1, the artificial intelligence tool is considered the approach to adopt in modelling electricity demand for Nigeria. According to Saglam et al (2023), the analytical instruments for modelling electricity can be categorised into traditional and artificial intelligence-based methods. However, our model applies the AI-supported algorithm because of its advantages over the traditional model.…”

“…The study concluded that ANN provided a better forecast based on MAPE evaluation. In the same vein, Saglam et al (2023) conducted a similar analysis for Tukey using the Medium Neural Network (MNN), Whale Optimization (WAO), and Support Vector Machine (SVM) for modelling electricity demand for 2040. Yearly time series between 1980 and 2019 were used for the model.…”

Instantaneous Electricity Peak Load Forecasting Using Optimization and Machine Learning

“…Excessive activations of power supply units, resulting in increased energy consumption and surplus reserves, occur when the load estimates exceed electricity demands. Conversely, lower load projections can push the system into a precarious situation, leading to insufficient supply [9]. Nonetheless, load and demand forecasts serve as the foundation for various decisions in the energy market, enabling the efficient, transparent, and dependable planning and administration of electricity markets to meet the sector's requirements [10].…”

“…Recently, researchers have recognized the effectiveness of combining various methods, leading to the development of hybrid models to improve prediction accuracy. These hybrid models integrate techniques such as traditional forecasting models (e.g., linear regression and grey models), seasonal adjustment/quarterly average methods, and intelligent optimization algorithms like PSO [45], sine cosine algorithm (SCA) [46], and whale optimization algorithm (WOA) [9,47], among others. As a result, numerous hybrid forecasting models have emerged and are used in applications in various domains, including electricity load and price prediction [48][49][50][51] and wind energy prediction [32,52,53].…”

Multilayer LSTM Model for Wind Power Estimation in the Scada System

“…If the power predictions are miscalculated, the energy production of the turbines may be lower or higher than expected. This can complicate the efficient use of resources and affect the stability of the energy grid [5]. Therefore, accurate active power forecasts are one of the key factors in the success of the wind energy industry [6].…”